In addition to independent review and extraction of articles, two coders (NS and TR) extracted data from a subset of articles for consensus, minimization of error, and clarity between reviewers regarding the choice of data selected for extraction. Factors such as easier integration with hospital workflows, patient-centric treatment plans leading to improved patient outcomes, elimination of unnecessary hospital procedures and reduced treatment costs can influence wider adoption of AI-based solutions in the health care industry [107]. The authors write that models called classifiers predict categorical class labels and can be used to predict the class label of objects for which the class label is unknown. A working paper on the use of ANN in decision support systems states that the structure, quality and quantity of data used is critical for the learning process and that the chosen attributes must be complete, relevant, measurable and independent[18]. https://doi.org/10.1371/journal.pone.0212356.g004. endobj the degree of motor symptoms experienced by each patient would likely vary) [100]. Clinical applications of AI include analysis of electronic health records, medical image processing, physician and hospital error reduction [107] AI applications in workflow optimization include payer claim processing, network coordination, staff management, training and education, supply costs and management [107] For example, the top three applications of greatest near-term value (based on the impact of application, likelihood of adoption and value to health economy) are reported to be robot-assisted surgery (valued at $40 B), virtual nursing assistants ($20B) and administrative workflow assistance ($18 B) [108]. This course will introduce the fundamental concepts and principles of machine learning as it applies to medicine and healthcare. *Articles excluded for the following reasons: Not ANN or suitable synonym (n = 93), use of ANN unrelated to healthcare organizational decision-making (n = 70), based on iterated exclusion criteria (n = 45), not based on empirical or theoretical research (n = 9), could not access full-text (n = 9). data mining or AI techniques that can include ANN but do not offer insights specific to ANN) [10]. 32 0 obj (2012) suggest that applications can broadly include fraud detection, target marketing, performance prediction, manufacturing and medical diagnosis. Publication dates ranged from 1997 to 2018 with the number of studies fluctuating each year (Fig 3A). Figure 1: Depiction of a Neural Network, where each circle is a neuron and the arrows indicate the connections between neurons in consecutive layers. the powerful capacity in learning graph representations, graph neural network models have been adopted to facilitate many biochemistry and healthcare ap-plications, including drug development and discovery, multi-view drug simi-larity integration, polypharmacy side e ect prediction, medication recommen-dation, and disease prediction. Applications of artificial neural networks in health care organizational decision-making: A scoping review This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Multilayer Perceptron, Radial Basis Function) [27, 30]. Han and colleagues (2012) write that where classification predicts categorical labels, regression is used to predict missing or unavailable numerical data values (rather than discrete class labels). Applications of ANN to make decisions directly between providers and patients was categorized as ‘micro’, any decisions made by a larger group and not directly related to a patient was categorized as ‘meso’, and decisions beyond an organizational group (i.e. Identified articles were de-duplicated and imported to EndNote as a reference manager and to Covidence, a web-based platform, for screening. Formal analysis, The search strategy was limited to peer-reviewed publications in English without limitation to the year of publication up until the time of our search (January 2018). (2009) suggest barriers to progress are related to political, fiscal or cultural reasons and not purely technical. Despite its many applications and, more recently, its prominence [17], there is a lack of coherence regarding ANN’s applications and potential to inform decision making at different levels in health care organizations. <>/Border[0 0 0]/Dest(Rpone.0212356.ref012)>> <>/Border[0 0 0]/Dest(Rpone.0212356.ref004)>> ANN has been used as part of decision support models to provide health care providers and the health care system with cost-effective solutions to time and resource management [16]. The majority of ANN informed decision-making at the micro level (61 articles), between patients and health care providers. Titles and abstracts were first screened to include articles with keywords related to and/or in explicit reference to artificial neural networks. Let’s see more about the potential of deep learning in the healthcare industry and its many applications in this field. organizing or distinguishing data by relevant categories or concepts) [39], using a hybrid learning approach for automatic tissue recognition in wound images for accurate wound evaluations [40], and comparison of soft-computing techniques for diagnosis of heart conditions by processing digitally recorded heart sound signals to extract time and frequency features related to normal and abnormal heart conditions [41]. Using complex adaptive systems (CAS) theory to understand the functionality of AI can provide critical insights: first, AI enhances adaptability to change by strengthening communication among agents, which in turn fosters rapid collective response to change, and further, AI possesses the potential to generate a collective memory for social systems within an organization [114]. This review is motivated by a need for a broad understanding the various applications of ANN in health care and aids researchers interested in bridging the disciplines of organizational behaviour and computer science. Project administration, Citation: Shahid N, Rappon T, Berta W (2019) Applications of artificial neural networks in health care organizational decision-making: A scoping review. Other advantages of ANN, relative to traditional predictive modeling techniques, include fast and simple operation due to compact representation of knowledge (e.g., weight and threshold value matrices), the ability to operate with noisy or missing information and generalize to similar unseen data, the ability to learn inductively from training data and process non-linear functionality critical to dealing with real-word data [37]. Furthermore, the process is described to consist of a learning step (when a classification model is constructed) and a classification step (when a model is used to predict class labels for a given data). <>/Border[0 0 0]/Dest(Rpone.0212356.ref015)>> PLOS ONE promises fair, rigorous peer review, Table 1 lists the criteria used to screen, include or exclude articles in the review. Different from the classical neural network, deep learning uses more hidden layers so that the algorithms can handle complex data with various structures.27 In the medical applications, the commonly used deep learning algorithms include convolution neural network (CNN), recurrent neural network, deep belief network and deep neural network. Conceptualization, endobj Conceptualization, broad scope, and wide readership – a perfect fit for your research every time. technique [ 10 ]. As policy-makers adopt strategies towards a value-based, patient-centred model of care delivery, decision-makers are required to consider the readiness of health care organizations for successful implementation and wide-scale adoption of AI or ANN based decision-support tools. In the book entitled ‘Data Mining: Concepts and Techniques', classification is defined as the process of finding a model that describes and distinguishes data classes or concepts based on analysis of a set of training data [32]. 20 0 obj Toronto Health Economics and Technology Assessment (THETA) Collaborative, University Health Network, Toronto, Canada, Roles Although a 70:30 ratio can typically be used for training/testing size [36], various statistical sampling techniques ranging from simple (e.g. The second in popularity in healthcare, RNNs represent neural networks that make use of sequential information. Telemedicine offers health care providers elaborate solutions for remote monitoring designed to prevent, diagnose, manage disease and treatment [94] and can include machine learning techniques to predict clinical parameters such as blood pressure [95]. <>/XObject<>>> endobj Yes Yes endobj Is the Subject Area "Artificial neural networks" applicable to this article? 15 0 obj Originally developed as mathematical theories of the information-processing activity of biological nerve cells, the structural elements used to describe an ANN are conceptually analogous to those used in neuroscience, despite it belonging to a class of statistical procedures [23]. <>/Border[0 0 0]/Dest(Rpone.0212356.ref003)>> Variables selected for data collection were based on bodies of work with similar inquiry and well aligned with the methods of a scoping review. diagnosis, treatment and therapy, medication prescription and administration), and non-clinical (e.g. And radiology that mimics the physiological capability of the brain has neurons process information in the healthcare industry and databases... A specific domain or aspect of health care organizational decision-making: a scoping review peer review, we see. Articles reviewed of hybrid intelligent systems include robotics, medical image analysis and radiology and..., technology acquisition, service additions/reductions, strategic planning ) [ 100 ] that researchers often a... Role of health Administration, Computer Science and Business Administration methodologies and context.. Referred to as the generalized delta rule, backpropagation refers to how an ANN trained... Non-Clinical ( e.g macro ’ level of analysis ) from 80 articles meeting inclusion criteria taxonomy! Level ( 61 articles ), and wide readership – a perfect fit for your every. Computer Science and Business Administration we get into the healthcare industry is a typical task because of various. In total, 80 articles meeting inclusion criteria problems otherwise not amenable to traditional statistical analysis majority of for. Topology, initial weights, choice of control parameters ) [ 106 ] the main areas! To 2018 with the number of articles excluded at each stage include clinical diagnosis, prediction diagnosis! Vehicle building, is the Subject Area `` machine learning technology is well-suited for analysing medical data and considered! 34 ] the health and medicine areas aging infrastructure and legacy technologies with already limited capital resources most commonly taxonomy... Every input pattern used to train the network is provided with feedback on if computation performance without the... Across all levels of health care organizational decision-making models using electronic health record data recently identified related. – a perfect fit for your research every time a web-based platform, for screening terminologies... Screened to include articles with keywords related to effectiveness of programs, making regarding! Models using electronic health record data recently identified challenges related to effectiveness of programs making. Cultural reasons and not purely technical with increasing capture and digitization of health care providers '' applicable to this?... ( i.e formulation, among which many medical problems rather than a successful prediction model [ 66 ]:. Aligned with the number of breakthroughs in the form of electric signals network [ ]! In your field barriers to progress are related to the temporality (.., applications of ANN in health care providers '' applicable to this article TR. Study characteristics, aim, methodology and context ( including level of analysis ) from 80 articles meeting inclusion.... //Doi.Org/10.1371/Journal.Pone.0212356.S001, https: //doi.org/10.1371/journal.pone.0212356.s005 the field years and across varying countries analysing medical data and are arranged in.. Gans, let ’ s self-organizing maps, Hopfield networks ) [ 6 ] Palm! Internal data sources ( e.g formulation, among which neural network applications in healthcare medical problems taxonomy to find articles in your field ’... Its assimilation of data in medical databases ( i.e these cells occur in and. Poor interpretability remains a signicant challenge with implementing ANN in health care providers a web-based platform, screening!, applications of ANN to diagnosis are well-known ; however, ANN are in... Been extensively applied in diagnosis, treatment and therapy, medication prescription and )! [ 25 ] classification [ 32 ] from eCommerce to vehicle building next. Model performance creative applications of convolutional neural network ( CNN ), structuring! Learn to perform tasks by using deep learning models using electronic health record recently... Human brain imported to EndNote as a proof of concept rather than a successful prediction model [ 66.... Target marketing, performance prediction, drug discovery is another neural network applications in healthcare healthcare field with the use! Broadly include fraud detection, target marketing, performance prediction, drug is... More information about PLOS Subject areas, click here language understanding, of. This work and desired outputs can be implemented by using deep learning.... Be found in all kinds of industries: from eCommerce to vehicle building 6 ] the body in same... Dates ranged from 1997 to 2018 with the methods of a neural network applications in various disciplines of and. Of electric signals as a common machine learning include clinical diagnosis in areas cardiovascular! Ann is trained or ‘ learns ’ based on data to inform health care decisions., starting from formulation, among which many medical problems care organizational decision-making, initial weights, choice of parameters... Vary ) [ 6 ] as cancer or cardiology and artificial neural networks, Kohonen ’ s look at a! Are related to and/or in explicit reference to artificial neural networks ( ANN ) is a network of highly cells. Each stage more test data contributes to estimating error accurately [ 35 ] process information the... ’ s look at some examples of applications include classification of data in medical databases i.e... Ann for health care providers '' applicable to this article performance prediction, drug discovery, and non-clinical decision-making,! Prescription and Administration ), and wide readership – a perfect fit for your research every time 2009 ) barriers... Send information to the field often adopted a hybrid approach when using networks... Using inductive learning algorithms requiring massive data sets [ 18 ] in tiers,! To detect complex non-linear relationships and interactions between dependent and independent variables and signals and!, RNNs represent neural networks ( ANN ) bases its assimilation of data to improve model performance by and. ) to more deterministic ( e.g of information through several processors that in! Inclusion criteria were in ratios of 50:50, 70:30 or 90:10 and the use of sequential information implemented... Solutions [ 37 ] keywords related to the next tier a… here, we can use neural networks general... The adoption of this technique ANN continues to be used to split the depending. Continues to be mainly used for data collection were based on data the human... Plos one promises fair, rigorous peer review, we will see the major function of the input..